Fiji-FIN: A Fault Injection Framework on Quantized Neural Network Inference Accelerator
Date of Original Version
In recent years, the big data booming has boosted the development of highly accurate prediction models driven from machine learning (ML) and deep learning (DL) algorithms. These models can be orchestrated on the customized hardware in the safety-critical missions to accelerate the inference process in ML/DL -powered IoT. However, the radiation-induced transient faults and black/white -box attacks can potentially impact the individual parameters in ML/DL models which may result in generating noisy data/labels or compromising the pre-trained model. In this paper, we propose Fiji-FIN 1, a suitable framework for evaluating the resiliency of IoT devices during the ML/DL model execution with respect to the major security challenges such as bit perturbation attacks and soft errors. Fiji-FIN is capable of injecting both single bit/event flip/upset and multi-bit flip/upset faults on the architectural ML/DL accelerator embedded in ML/DL -powered IoT. Fiji-FIN is significantly more accurate compared to the existing software-level fault injections paradigms on ML/DL -driven IoT devices.
Proceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
Khoshavi, Navid, Connor Broyles, Yu Bi, and Arman Roohi. "Fiji-FIN: A Fault Injection Framework on Quantized Neural Network Inference Accelerator." Proceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020 , (2020): 1139-1144. doi:10.1109/ICMLA51294.2020.00183.